SlideShare a Scribd company logo
1 of 37
A Novel Motion Monitoring System for
Activities of Daily Living
Xiang He
New York Institute of Technology
Old Westbury, NY
October 2015
1. Activities of daily living (ADLs)
2. Novel motion monitoring system
3. Tests and results
4. Conclusion
5. Future work
Content
1. Activities of daily living (ADLs)
Activities of daily living examples
Problems:
ā€¢High healthcare cost
ā€¢In lack of proactive healthcare
1. Activities of daily living (ADLs)
1. Activities of daily living (ADLs)
2. Novel motion monitoring system
3. Tests and results
4. Conclusion
5. Future work
Content
2. Novel motion monitoring system
Markerless or marker-based motion capture (mo-cap) system
VS
inertial measurement unit (IMU) based mo-cap system
2. Novel motion monitoring system
2. Novel motion monitoring system
Quaternion algorithm
Quaternion
šµ
š“
š‘ž = [š‘ž1 š‘ž2 š‘ž3 š‘ž4] = cos
šœƒ
2
āˆ’ š‘Ÿš‘„ sin
šœƒ
2
āˆ’ š‘Ÿš‘¦ sin
šœƒ
2
āˆ’ š‘Ÿš‘§ sin
šœƒ
2
Gyroscope
Angular rate
Accelerometer
Direction of gravity
Magnetometer
Direction of magnetic field
Defection angles roll (X), pitch (Y) and yaw (Z)
2. Novel motion monitoring system
2. Novel motion monitoring system
Motion trajectory reconstruction
(š‘Ž š‘„ , š‘Ž š‘¦ , š‘Ž š‘§ )
(š‘” š‘„ , š‘” š‘¦ , š‘” š‘§ )
(š‘š š‘„ , š‘š š‘¦ , š‘š š‘§ )
Quaternion
Algorithm
Defection angles in
three axis (roll,
pitch and yaw)
Acceleration
Velocity
Displacement
2. Novel motion monitoring system
System architecture
Data collection
using a IMU-based
device
Real-time signal
displaying and
saving program
2. Novel motion monitoring system
The IMU-based device: SensorTag (Texas Instruments)
2. Novel motion monitoring system
SensorTag components
2. Novel motion monitoring system
Sensorsā€™ sampling rates and data range
2. Novel motion monitoring system
SensorTag firmware flowchart
ā€¢ Initialize the device and advertise
ā€¢ Turn on sensors and send data
ā€¢ Disable sensors and back to
advertising status
2. Novel motion monitoring system
SensorTag connection with smartphone and laptop
2. Novel motion monitoring system
BLE connection with smartphone
2. Novel motion monitoring system
LabVIEW program flowchart
ā€¢ Establish the connection
ā€¢ Read and display signals
ā€¢ Save data and disconnect
2. Novel motion monitoring system
Signalsā€™ display and save
1. Activities of daily living (ADLs)
2. Novel motion monitoring system
3. Tests and results
4. Conclusion
5. Future work
Content
3. Tests and results
ā€¢Linear displacement measuring
ā€¢Eating gesture monitoring
ā€¢Walking monitoring
3. Tests and results
ā€¢Linear displacement measuring experiment
ā€¢Eating gesture monitoring
ā€¢Walking monitoring
3. Three experiments
ā€¢Linear displacement measuring experiment
ā€¢SensorTag system
3. Three experiments
ā€¢Linear displacement measuring experiment
ā€¢SensorTag system
3. Three experiments
ā€¢Linear displacement measuring experiment
ā€¢Marker-based mo-cap system
3. Three experiments
ā€¢SensorTag system displacement measurement error rate
ā€¢Linear displacement measuring experiment
ā€¢Marker-based mo-cap system
3. Three experiments
ā€¢Eating gesture monitoring
1 2 3 4
3. Three experiments
ā€¢Eating gesture monitoring
3. Three experiments
ā€¢Eating gesture monitoring
3. Three experiments
ā€¢Walking monitoring
3. Three experiments
ā€¢Walking monitoring
ā€¢Left and right wrists
3. Three experiments
ā€¢Walking monitoring
ā€¢Left and right knees
3. Three experiments
ā€¢Walking monitoring
ā€¢Left and right ankles
3. Three experiments
ā€¢Walking monitoring
ā€¢Ankle displacement measurement error rates
4. Conclusion
ā€¢The displacement measuring results are good for
linear motions.
ā€¢The algorithm failed to revise the direction during
eating gesture reconstruction.
5. Future work
ā€¢Angular and displacement computation.
ā€¢More convenient to use on smartphones.
5. Questions?
Thanks for your time.

More Related Content

Viewers also liked

ģƒė°©ģ†”ģ¹“ģ§€ė…ø ģ‚¬ģ“ķŠø ā‰«otp88.ļ½ƒļ½ļ½ā‰Ŗ ģƒģ¤‘ź³„ģ¹“ģ§€ė…ø ģƒė°©ģ†”ėø”ėž™ģž­nd9
ģƒė°©ģ†”ģ¹“ģ§€ė…ø ģ‚¬ģ“ķŠø ā‰«otp88.ļ½ƒļ½ļ½ā‰Ŗ ģƒģ¤‘ź³„ģ¹“ģ§€ė…ø ģƒė°©ģ†”ėø”ėž™ģž­nd9 ģƒė°©ģ†”ģ¹“ģ§€ė…ø ģ‚¬ģ“ķŠø ā‰«otp88.ļ½ƒļ½ļ½ā‰Ŗ ģƒģ¤‘ź³„ģ¹“ģ§€ė…ø ģƒė°©ģ†”ėø”ėž™ģž­nd9
ģƒė°©ģ†”ģ¹“ģ§€ė…ø ģ‚¬ģ“ķŠø ā‰«otp88.ļ½ƒļ½ļ½ā‰Ŗ ģƒģ¤‘ź³„ģ¹“ģ§€ė…ø ģƒė°©ģ†”ėø”ėž™ģž­nd9 rlaehdrb212
Ā 
Model Analysis of Cymbal Generator Under Different Working Conditions
Model Analysis of Cymbal Generator Under Different Working ConditionsModel Analysis of Cymbal Generator Under Different Working Conditions
Model Analysis of Cymbal Generator Under Different Working ConditionsIJRES Journal
Ā 
xRM4Legal for the Call Center Web2CRM
xRM4Legal for the Call Center Web2CRMxRM4Legal for the Call Center Web2CRM
xRM4Legal for the Call Center Web2CRMDavid Blumentals
Ā 
Quaternions - Phoenix Bird presentation, v23
Quaternions - Phoenix Bird presentation, v23Quaternions - Phoenix Bird presentation, v23
Quaternions - Phoenix Bird presentation, v23Herb Klitzner
Ā 
1.introduction to quality & total quality management
1.introduction to quality & total quality management1.introduction to quality & total quality management
1.introduction to quality & total quality managementHakeem-Ur- Rehman
Ā 
Mobile voting by using biometrics
Mobile  voting  by  using biometricsMobile  voting  by  using biometrics
Mobile voting by using biometricsJEEVA ARAVINTH
Ā 

Viewers also liked (8)

ģƒė°©ģ†”ģ¹“ģ§€ė…ø ģ‚¬ģ“ķŠø ā‰«otp88.ļ½ƒļ½ļ½ā‰Ŗ ģƒģ¤‘ź³„ģ¹“ģ§€ė…ø ģƒė°©ģ†”ėø”ėž™ģž­nd9
ģƒė°©ģ†”ģ¹“ģ§€ė…ø ģ‚¬ģ“ķŠø ā‰«otp88.ļ½ƒļ½ļ½ā‰Ŗ ģƒģ¤‘ź³„ģ¹“ģ§€ė…ø ģƒė°©ģ†”ėø”ėž™ģž­nd9 ģƒė°©ģ†”ģ¹“ģ§€ė…ø ģ‚¬ģ“ķŠø ā‰«otp88.ļ½ƒļ½ļ½ā‰Ŗ ģƒģ¤‘ź³„ģ¹“ģ§€ė…ø ģƒė°©ģ†”ėø”ėž™ģž­nd9
ģƒė°©ģ†”ģ¹“ģ§€ė…ø ģ‚¬ģ“ķŠø ā‰«otp88.ļ½ƒļ½ļ½ā‰Ŗ ģƒģ¤‘ź³„ģ¹“ģ§€ė…ø ģƒė°©ģ†”ėø”ėž™ģž­nd9
Ā 
Model Analysis of Cymbal Generator Under Different Working Conditions
Model Analysis of Cymbal Generator Under Different Working ConditionsModel Analysis of Cymbal Generator Under Different Working Conditions
Model Analysis of Cymbal Generator Under Different Working Conditions
Ā 
xRM4Legal for the Call Center Web2CRM
xRM4Legal for the Call Center Web2CRMxRM4Legal for the Call Center Web2CRM
xRM4Legal for the Call Center Web2CRM
Ā 
Quaternions - Phoenix Bird presentation, v23
Quaternions - Phoenix Bird presentation, v23Quaternions - Phoenix Bird presentation, v23
Quaternions - Phoenix Bird presentation, v23
Ā 
1.introduction to quality & total quality management
1.introduction to quality & total quality management1.introduction to quality & total quality management
1.introduction to quality & total quality management
Ā 
Mobile voting by using biometrics
Mobile  voting  by  using biometricsMobile  voting  by  using biometrics
Mobile voting by using biometrics
Ā 
Š°Ń€Ń‚ тŠµŃ€Š°ŠæŠøя
Š°Ń€Ń‚ тŠµŃ€Š°ŠæŠøяŠ°Ń€Ń‚ тŠµŃ€Š°ŠæŠøя
Š°Ń€Ń‚ тŠµŃ€Š°ŠæŠøя
Ā 
April 2015
April 2015April 2015
April 2015
Ā 

Similar to Novel IMU-Based Motion Monitoring for Daily Activities

Elderly activity recognition and classification for application in assisted l...
Elderly activity recognition and classification for application in assisted l...Elderly activity recognition and classification for application in assisted l...
Elderly activity recognition and classification for application in assisted l...Sara Egidi
Ā 
Long durationspaceflightoct01
Long durationspaceflightoct01Long durationspaceflightoct01
Long durationspaceflightoct01Clifford Stone
Ā 
Evaluating a Potential Commercial Tool for Healthcare Application for People ...
Evaluating a Potential Commercial Tool for Healthcare Application for People ...Evaluating a Potential Commercial Tool for Healthcare Application for People ...
Evaluating a Potential Commercial Tool for Healthcare Application for People ...Artificial Intelligence Institute at UofSC
Ā 
ToBITas Case Study, Presentation for UCAMI 2014 conference
ToBITas Case Study, Presentation for UCAMI 2014 conferenceToBITas Case Study, Presentation for UCAMI 2014 conference
ToBITas Case Study, Presentation for UCAMI 2014 conferenceBorja Gamecho
Ā 
A combined approach for anomaly detection in production systems using ML tech...
A combined approach for anomaly detection in production systems using ML tech...A combined approach for anomaly detection in production systems using ML tech...
A combined approach for anomaly detection in production systems using ML tech...za_slide
Ā 
Recent advances on motion analysis in sports
Recent advances on motion analysis  in sportsRecent advances on motion analysis  in sports
Recent advances on motion analysis in sportspunita85
Ā 
Measuring and quantifying quality of movement
Measuring and quantifying quality of movementMeasuring and quantifying quality of movement
Measuring and quantifying quality of movementJustyna Ausareny
Ā 
Improving Activity Monitoring through a Hierarchical Approach
Improving Activity Monitoring through a Hierarchical ApproachImproving Activity Monitoring through a Hierarchical Approach
Improving Activity Monitoring through a Hierarchical ApproachXavier Rafael Palou
Ā 
A Movement Recognition Method using LBP
A Movement Recognition Method using LBPA Movement Recognition Method using LBP
A Movement Recognition Method using LBPZihui Li
Ā 
Knee Osteoarthritis Classification System Examination on Wearable Daily-Use I...
Knee Osteoarthritis Classification System Examination on Wearable Daily-Use I...Knee Osteoarthritis Classification System Examination on Wearable Daily-Use I...
Knee Osteoarthritis Classification System Examination on Wearable Daily-Use I...sugiuralab
Ā 
A System Dynamics Model of the 2005 Hatlestad Slide Emergency Management
A System Dynamics Model of the 2005 Hatlestad Slide Emergency Management A System Dynamics Model of the 2005 Hatlestad Slide Emergency Management
A System Dynamics Model of the 2005 Hatlestad Slide Emergency Management streamspotter
Ā 
Introduction to Mechatronics Systems- An Overview
Introduction to Mechatronics Systems- An OverviewIntroduction to Mechatronics Systems- An Overview
Introduction to Mechatronics Systems- An OverviewFebinSuresh2
Ā 
feature processing and modelling for 6D motion gesture database.....
feature processing and modelling for 6D motion gesture database.....feature processing and modelling for 6D motion gesture database.....
feature processing and modelling for 6D motion gesture database.....jcmcsiit
Ā 
CONDITION MONITORING
CONDITION MONITORINGCONDITION MONITORING
CONDITION MONITORINGlaxtwinsme
Ā 
Earthquake Detector.pdf
Earthquake Detector.pdfEarthquake Detector.pdf
Earthquake Detector.pdfKunalSonawane26
Ā 
Earthquake Detector.pdf
Earthquake Detector.pdfEarthquake Detector.pdf
Earthquake Detector.pdfKunalSonawane26
Ā 
human activity recognization using machine learning with data analysis
human activity recognization using machine learning with data analysishuman activity recognization using machine learning with data analysis
human activity recognization using machine learning with data analysisVenkat Projects
Ā 

Similar to Novel IMU-Based Motion Monitoring for Daily Activities (20)

Elderly activity recognition and classification for application in assisted l...
Elderly activity recognition and classification for application in assisted l...Elderly activity recognition and classification for application in assisted l...
Elderly activity recognition and classification for application in assisted l...
Ā 
Long durationspaceflightoct01
Long durationspaceflightoct01Long durationspaceflightoct01
Long durationspaceflightoct01
Ā 
Evaluating a Potential Commercial Tool for Healthcare Application for People ...
Evaluating a Potential Commercial Tool for Healthcare Application for People ...Evaluating a Potential Commercial Tool for Healthcare Application for People ...
Evaluating a Potential Commercial Tool for Healthcare Application for People ...
Ā 
ToBITas Case Study, Presentation for UCAMI 2014 conference
ToBITas Case Study, Presentation for UCAMI 2014 conferenceToBITas Case Study, Presentation for UCAMI 2014 conference
ToBITas Case Study, Presentation for UCAMI 2014 conference
Ā 
A combined approach for anomaly detection in production systems using ML tech...
A combined approach for anomaly detection in production systems using ML tech...A combined approach for anomaly detection in production systems using ML tech...
A combined approach for anomaly detection in production systems using ML tech...
Ā 
Recent advances on motion analysis in sports
Recent advances on motion analysis  in sportsRecent advances on motion analysis  in sports
Recent advances on motion analysis in sports
Ā 
Sistema di misura per la valutazione del cammino
Sistema di misura per la valutazione del camminoSistema di misura per la valutazione del cammino
Sistema di misura per la valutazione del cammino
Ā 
Measuring and quantifying quality of movement
Measuring and quantifying quality of movementMeasuring and quantifying quality of movement
Measuring and quantifying quality of movement
Ā 
Improving Activity Monitoring through a Hierarchical Approach
Improving Activity Monitoring through a Hierarchical ApproachImproving Activity Monitoring through a Hierarchical Approach
Improving Activity Monitoring through a Hierarchical Approach
Ā 
372814
372814372814
372814
Ā 
A Movement Recognition Method using LBP
A Movement Recognition Method using LBPA Movement Recognition Method using LBP
A Movement Recognition Method using LBP
Ā 
Knee Osteoarthritis Classification System Examination on Wearable Daily-Use I...
Knee Osteoarthritis Classification System Examination on Wearable Daily-Use I...Knee Osteoarthritis Classification System Examination on Wearable Daily-Use I...
Knee Osteoarthritis Classification System Examination on Wearable Daily-Use I...
Ā 
A System Dynamics Model of the 2005 Hatlestad Slide Emergency Management
A System Dynamics Model of the 2005 Hatlestad Slide Emergency Management A System Dynamics Model of the 2005 Hatlestad Slide Emergency Management
A System Dynamics Model of the 2005 Hatlestad Slide Emergency Management
Ā 
Presentation
PresentationPresentation
Presentation
Ā 
Introduction to Mechatronics Systems- An Overview
Introduction to Mechatronics Systems- An OverviewIntroduction to Mechatronics Systems- An Overview
Introduction to Mechatronics Systems- An Overview
Ā 
feature processing and modelling for 6D motion gesture database.....
feature processing and modelling for 6D motion gesture database.....feature processing and modelling for 6D motion gesture database.....
feature processing and modelling for 6D motion gesture database.....
Ā 
CONDITION MONITORING
CONDITION MONITORINGCONDITION MONITORING
CONDITION MONITORING
Ā 
Earthquake Detector.pdf
Earthquake Detector.pdfEarthquake Detector.pdf
Earthquake Detector.pdf
Ā 
Earthquake Detector.pdf
Earthquake Detector.pdfEarthquake Detector.pdf
Earthquake Detector.pdf
Ā 
human activity recognization using machine learning with data analysis
human activity recognization using machine learning with data analysishuman activity recognization using machine learning with data analysis
human activity recognization using machine learning with data analysis
Ā 

Novel IMU-Based Motion Monitoring for Daily Activities

Editor's Notes

  1. Thank you for your time.
  2. What are ADLs and whatā€™s the purpose of applying a motion monitoring system to healthcare?
  3. Very hard for the elderly, disabled, and chronic disease patients.
  4. A real-time ADLs motion monitoring system can help.
  5. Markerless and marker-based mo-cap system are used for animation and filming. They are set up in camera studios and very expensive, although they are accurate. On the other hand, IMU-based system is cheaper and wearable.
  6. Markerless and marker-based mo-cap usually have nine or more cameras. Depth sensing like Microsoft Kinect only has three cameras at most. Electromyography (EMG) measures the electrical activity produced by skeletal muscles.
  7. Quaternion is used to represent the orientation including three types of deflection angles roll (X), pitch (Y) and yaw (Z).
  8. Markerless and marker-based mo-cap usually have nine or more cameras. Depth sensing like Microsoft Kinect only has three cameras at most. Electromyography (EMG) measures the electrical activity produced by skeletal muscles.
  9. The direction angles is computed in quaternion, and then use the accelerometer data for acceleration, velocity and displacement calculation.
  10. Small to be wearable.
  11. Only use three sensors. CC2541 is an ultra low power system on chip (SoC) Bluetooth low energy (BLE) solution.
  12. The sampling rate ranges of accelerometer and gyroscope are very wide, but gyroscope consumes very much power with 200Hz or higher, and the magnetometer can only achieve 80Hz at most, thus I only tests up to 100Hz to collect enough data and gain more power savings.
  13. Operating System Abstraction Layer (OSAL) is used in Bluetooth low energy (BLE) protocol. It schedules events in BLE application, and the eleventh one is SensorTag event to perform read and write.
  14. Classic Bluetooth canā€™t communicate with BLE or Bluetooth smart. Bluetooth smart ready devices can pair with two previous kinds of devices.
  15. Up to seven slave devices can be connected to one central device.
  16. 10 seconds to scan for devices and reading starts in 5 seconds after connection.
  17. Data and timestamp save in txt files.
  18. Test the system with displacement measuring error rates, and try to rebuild the two ADLs.
  19. Motion capture lab with 9 cameras. Move the SensorTag along the ruler for 60cm and stop for 1 second every 10cm.
  20. The hand failed to move the SensorTag in a straight line.
  21. Prove the potential to rebuild the motion
  22. Prove the potential to rebuild the motion
  23. Walk 13ft, which is 3.9624m. The ceramic tile is a 1ft-side-length square.
  24. Wrists moved shorter for relative displacement.
  25. For stable long-term angular calculation, it might help to use a better gyroscope and the algorithm needs more improvements.
  26. Develop a better orientation algorithm based on quaternion. Increase the three sensorsā€™ sampling rates. Apply CC2650 with better accelerometer, gyroscope and magnetometer or to build a customized circuit. Develop a smartphone application to connect six SensorTags.